Unsupervised Mixture Models on the Edge for Smart Energy Consumption Segmentation with Feature Saliency
Smart meter datasets have recently transitioned from monthly intervals to one-second granularity, yielding invaluable insights for diverse metering functions. Clustering analysis, a fundamental data mining technique, is extensively applied to discern unique energy consumption patterns. However, the...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/19/8296 |
| _version_ | 1797575158625468416 |
|---|---|
| author | Hussein Al-Bazzaz Muhammad Azam Manar Amayri Nizar Bouguila |
| author_facet | Hussein Al-Bazzaz Muhammad Azam Manar Amayri Nizar Bouguila |
| author_sort | Hussein Al-Bazzaz |
| collection | DOAJ |
| description | Smart meter datasets have recently transitioned from monthly intervals to one-second granularity, yielding invaluable insights for diverse metering functions. Clustering analysis, a fundamental data mining technique, is extensively applied to discern unique energy consumption patterns. However, the advent of high-resolution smart meter data brings forth formidable challenges, including non-Gaussian data distributions, unknown cluster counts, and varying feature importance within high-dimensional spaces. This article introduces an innovative learning framework integrating the expectation-maximization algorithm with the minimum message length criterion. This unified approach enables concurrent feature and model selection, finely tuned for the proposed bounded asymmetric generalized Gaussian mixture model with feature saliency. Our experiments aim to replicate an efficient smart meter data analysis scenario by incorporating three distinct feature extraction methods. We rigorously validate the clustering efficacy of our proposed algorithm against several state-of-the-art approaches, employing diverse performance metrics across synthetic and real smart meter datasets. The clusters that we identify effectively highlight variations in residential energy consumption, furnishing utility companies with actionable insights for targeted demand reduction efforts. Moreover, we demonstrate our method’s robustness and real-world applicability by harnessing Concordia’s High-Performance Computing infrastructure. This facilitates efficient energy pattern characterization, particularly within smart meter environments involving edge cloud computing. Finally, we emphasize that our proposed mixture model outperforms three other models in this paper’s comparative study. We achieve superior performance compared to the non-bounded variant of the proposed mixture model by an average percentage improvement of 7.828%. |
| first_indexed | 2024-03-10T21:34:43Z |
| format | Article |
| id | doaj.art-7aca3848b18945bf9c82df6cf62196c7 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T21:34:43Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-7aca3848b18945bf9c82df6cf62196c72023-11-19T15:05:34ZengMDPI AGSensors1424-82202023-10-012319829610.3390/s23198296Unsupervised Mixture Models on the Edge for Smart Energy Consumption Segmentation with Feature SaliencyHussein Al-Bazzaz0Muhammad Azam1Manar Amayri2Nizar Bouguila3Concordia’s Institute for Information Systems Engineering (CIISE), Concordia University, Montreal, QC H3G 1M8, CanadaConcordia’s Institute for Information Systems Engineering (CIISE), Concordia University, Montreal, QC H3G 1M8, CanadaConcordia’s Institute for Information Systems Engineering (CIISE), Concordia University, Montreal, QC H3G 1M8, CanadaConcordia’s Institute for Information Systems Engineering (CIISE), Concordia University, Montreal, QC H3G 1M8, CanadaSmart meter datasets have recently transitioned from monthly intervals to one-second granularity, yielding invaluable insights for diverse metering functions. Clustering analysis, a fundamental data mining technique, is extensively applied to discern unique energy consumption patterns. However, the advent of high-resolution smart meter data brings forth formidable challenges, including non-Gaussian data distributions, unknown cluster counts, and varying feature importance within high-dimensional spaces. This article introduces an innovative learning framework integrating the expectation-maximization algorithm with the minimum message length criterion. This unified approach enables concurrent feature and model selection, finely tuned for the proposed bounded asymmetric generalized Gaussian mixture model with feature saliency. Our experiments aim to replicate an efficient smart meter data analysis scenario by incorporating three distinct feature extraction methods. We rigorously validate the clustering efficacy of our proposed algorithm against several state-of-the-art approaches, employing diverse performance metrics across synthetic and real smart meter datasets. The clusters that we identify effectively highlight variations in residential energy consumption, furnishing utility companies with actionable insights for targeted demand reduction efforts. Moreover, we demonstrate our method’s robustness and real-world applicability by harnessing Concordia’s High-Performance Computing infrastructure. This facilitates efficient energy pattern characterization, particularly within smart meter environments involving edge cloud computing. Finally, we emphasize that our proposed mixture model outperforms three other models in this paper’s comparative study. We achieve superior performance compared to the non-bounded variant of the proposed mixture model by an average percentage improvement of 7.828%.https://www.mdpi.com/1424-8220/23/19/8296probabilistic modellingenergy analyticsbounded mixture modelsasymmetric generalized Gaussian distributionfeature selection |
| spellingShingle | Hussein Al-Bazzaz Muhammad Azam Manar Amayri Nizar Bouguila Unsupervised Mixture Models on the Edge for Smart Energy Consumption Segmentation with Feature Saliency Sensors probabilistic modelling energy analytics bounded mixture models asymmetric generalized Gaussian distribution feature selection |
| title | Unsupervised Mixture Models on the Edge for Smart Energy Consumption Segmentation with Feature Saliency |
| title_full | Unsupervised Mixture Models on the Edge for Smart Energy Consumption Segmentation with Feature Saliency |
| title_fullStr | Unsupervised Mixture Models on the Edge for Smart Energy Consumption Segmentation with Feature Saliency |
| title_full_unstemmed | Unsupervised Mixture Models on the Edge for Smart Energy Consumption Segmentation with Feature Saliency |
| title_short | Unsupervised Mixture Models on the Edge for Smart Energy Consumption Segmentation with Feature Saliency |
| title_sort | unsupervised mixture models on the edge for smart energy consumption segmentation with feature saliency |
| topic | probabilistic modelling energy analytics bounded mixture models asymmetric generalized Gaussian distribution feature selection |
| url | https://www.mdpi.com/1424-8220/23/19/8296 |
| work_keys_str_mv | AT husseinalbazzaz unsupervisedmixturemodelsontheedgeforsmartenergyconsumptionsegmentationwithfeaturesaliency AT muhammadazam unsupervisedmixturemodelsontheedgeforsmartenergyconsumptionsegmentationwithfeaturesaliency AT manaramayri unsupervisedmixturemodelsontheedgeforsmartenergyconsumptionsegmentationwithfeaturesaliency AT nizarbouguila unsupervisedmixturemodelsontheedgeforsmartenergyconsumptionsegmentationwithfeaturesaliency |